Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of body parts or related actions

    oai_token-act-pair · gpt-3.5-turbo

    references to lips or lip-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùİ
    -0.81
    DERR
    -0.75
    IRD
    -0.75
     Leap
    -0.74
    ENCY
    -0.72
    ADRA
    -0.71
     à¨
    -0.70
     Rhino
    -0.69
    ISION
    -0.68
    IDER
    -0.66
    POSITIVE LOGITS
    atures
    1.02
    ids
    1.00
    etsk
    0.99
    sticks
    0.98
    ograph
    0.97
    oglobin
    0.92
    ocard
    0.91
    seys
    0.91
    ographs
    0.89
    stick
    0.88
    Act Density 0.015%

    No Known Activations